Awesome GitHub RepositoriesHigh-Performance Inference Modes

PaddleOCR is a comprehensive optical character recognition framework designed for detecting and transcribing text from images and documents into structured, machine-readable formats. It provides a modular computer vision pipeline that decouples image preprocessing, text detection, and character recognition into independent, configurable stages. This architecture supports automated document digitization and multilingual text recognition, capable of identifying text in over one hundred languages across diverse environments ranging from scanned documents to industrial scenes. The framework disti

This project is a distributed training infrastructure designed for aligning large language models through reinforcement learning. It functions as an end-to-end engine for complex alignment tasks, including proximal policy optimization, direct preference optimization, and iterative self-play. By providing a unified framework for multi-turn interactions and tool-use scenarios, it enables the development of models capable of reasoning and external environment engagement. The framework distinguishes itself through a decoupled architecture that separates model training from sample generation. This

This project is a comprehensive toolkit designed for the full lifecycle management of large language and multimodal models. It functions as a unified orchestrator that handles the entire development process, ranging from dataset preparation and supervised fine-tuning to advanced reinforcement learning alignment and production-ready inference deployment. The platform distinguishes itself through a specialized reinforcement learning library that supports complex optimization algorithms, including group relative policy optimization and leave-one-out techniques, to improve model instruction-follo

PaddleX is a PaddlePaddle-based framework for building, deploying, and fine-tuning AI model pipelines, with pre-built support for computer vision, OCR, document analysis, and time series tasks. It offers a toolkit of ready-to-use pipelines for image classification, object detection, segmentation, and pose estimation, alongside an end-to-end OCR document analysis pipeline that extracts text, tables, formulas, and layout information. The platform also includes a dedicated time series forecasting pipeline for analyzing historical data to detect anomalies, classify patterns, and predict future val

MindSpore este un framework de deep learning conceput pentru construirea și antrenarea rețelelor neuronale în medii cloud, edge și mobile. Acesta funcționează ca un sistem de antrenare distribuită și un toolkit AI accelerat hardware, capabil să execute sarcini pe CPU-uri, GPU-uri și procesoare AI specializate. Proiectul include un motor de diferențiere automată care calculează gradienții prin transformarea sursei și compilare statică. Acesta permite antrenarea distribuită a modelelor prin împărțirea sarcinilor pe hardware folosind paralelismul de date și de model. Framework-ul acoperă implementarea AI cross-platform și inferența modelelor, utilizând un toolkit de înaltă performanță pentru a accelera execuția și servirea. Oferă accelerare specializată pentru hardware-ul Ascend și suportă maparea operatorilor agnostică față de hardware pentru backend-uri de dispozitive eterogene. Mediul poate fi instalat printr-un manager de pachete sau compilat din sursă pe sisteme Linux pentru medii standard sau medii cu procesoare AI specializate.